123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437 |
- ---
- general:
- name: Divehi (Thaana)
- case_sensitive: false
- roman_to_script:
- map:
- # COMMON COMBINING CHARACTERS (always follow a base letter)
- # combining acute \u0301
- # combining tilde \u0303
- # combining macron \u0304
- # combining dot above \u0307
- # combining dot below \u0323
- # combining diaeresis below \u0324
- # combining low line \u0332
- # combining breve below \u032E
- # ayn (spacing) \u02BB
- # apostrophe (spacing) \u0027
- # REGULAR LATIN ALPHABETIC CHARACTERS TO BE CONVERTED
- # THAANA LETTER ALIF APPEARING MEDIALLY WITH ANY VOWEL IS ROMANIZED WITH APOSTROPHE
- # ORIGINAL VOWEL ASSOCIATED WITH THE ALIF CANNOT BE REGENERATED DURING CONVERSION
- "\u0027": "\u0787"
- # THAANA LETTER SHAVIYANI WITH SUKUN(BREVE 032E)
- "H\u032E": "\u0781\u07B0"
- "hh": "\u0787\u07B0\u0780"
- "h\u032E": "\u0781\u07B0"
- # THAANA LETTER ALIFU FINAL WITH SUKUN (LOW LINE 0332)
- "H\u0332%": "\u0787\u07B0"
- "h\u0332%": "\u0787\u07B0"
- "H": "\u0780"
- "h": "\u0780"
- "S\u0301": "\u0781"
- "ss": "\u0787\u07B0\u0781"
- "s\u0301": "\u0781"
- # THAANA LETTER MEDIAL NOONU WITHOUT SUKUN (DOT ABOVE 0307)
- "M\u0307": "\u0782"
- "m\u0307": "\u0782"
- "mm": "\u0787\u07B0\u0789"
- "N": "\u0782"
- "nn": "\u0787\u07B0\u0782"
- "n": "\u0782"
- "R": "\u0783"
- "rr": "\u0787\u07B0\u0783"
- "r": "\u0783"
- "B": "\u0784"
- "bb": "\u0787\u07B0\u0784"
- "b": "\u0784"
- # THAANA LETTER "L/l" WITH DOT BELOW (0323)
- "L\u0323": "\u0785"
- "l\u0323": "\u0785"
- "K": "\u0786"
- "kk": "\u0787\u07B0\u0786"
- "k": "\u0786"
- # THAANA LETTER ALIF--OFTEN OMITTED IN ROMANIZATION (SEE VOWEL CONVERSION BELOW)
- "\u0027": "\u0787"
- "V": "\u0788"
- "vv": "\u0787\u07B0\u0788"
- "v": "\u0788"
- "M": "\u0789"
- "m": "\u0789"
- "F": "\u078A"
- "ff": "\u0787\u07B0\u078A"
- "f": "\u078A"
- # THAANA LETTER "D/d" WITH DOT BELOW (0323)
- "D\u0323": "\u0791"
- "d\u0323": "\u0791"
- "D": "\u078B"
- "dd": "\u0787\u07B0\u078B"
- "d": "\u078B"
- # THAANA LETTER "T/t" WITH DOT BELOW (0323)
- "T\u0323": "\u0793"
- "t\u0323": "\u0793"
- "T\u0324T": "\u078C\u07B0\u078C"
- "T\u0324t": "\u078C\u07B0\u078C"
- "t\u0324t": "\u078C\u07B0\u078C"
- "t\u0324T": "\u078C\u07B0\u078C"
- "T": "\u078C"
- "tt": "\u0787\u07B0\u078C"
- "t": "\u078C"
- "L": "\u078D"
- "ll": "\u0787\u07B0\u078D"
- "l": "\u078D"
- "G": "\u078E"
- "gg": "\u0787\u07B0\u078E"
- "g": "\u078E"
- # THAANA LETTER "N/n' WITH TILDE (0303)
- "N\u0303": "\u078F"
- "n\u0303": "\u078F"
- "S": "\u0790"
- "ss": "\u0787\u07B0\u0790"
- "s": "\u0790"
- "Z": "\u0792"
- "zz": "\u0787\u07B0\u0792"
- "z": "\u0792"
- "Y": "\u0794"
- "yy": "\u0787\u07B0\u0794"
- "y": "\u0794"
- "P": "\u0795"
- "p": "\u0795"
- "pp": "\u0787\u07B0\u0795"
- "J": "\u0796"
- "jj": "\u0787\u07B0\u0796"
- "j": "\u0796"
- "C": "\u0797"
- "cc": "\u0787\u07B0\u0797"
- "c": "\u0797"
- # THAANA EXTENSION FOR ARABIC LOAN WORDS AND NAMES
- # THAANA EXTENSION FOR ARABIC LETTER TTAA
- "TH": "\u0798"
- "Th": "\u0798"
- "thth": "\u0787\u07B0\u0798"
- "th": "\u0798"
- # THAANA EXTENSION FOR ARABIC LETTER HHAA
- "H\u0323": "\u0799"
- "h\u0323": "\u0799"
- # THAANA EXTENSION FOR ARABIC LETTER KHAA
- "KH": "\u079A"
- "Kh": "\u079A"
- "khkh": "\u0787\u07B0\u079A"
- "kh": "\u079A"
- # THAANA EXTENSION FOR ARABIC LETTER THAALU
- "DH": "\u079B"
- "Dh": "\u079B"
- "dhdh": "\u0787\u07B0\u079B"
- "dh": "\u079B"
- # THAANA EXTENSION FOR ARABIC LETTER ZAA (NEWER LETTER)
- "Z\u0332": "\u079C"
- "z\u0332": "\u079C"
- # THAANA EXTENSION FOR ARABIC LETTER SHEENU
- "SH": "\u079D"
- "Sh": "\u079D"
- "shsh": "\u0787\u07B0\u079D"
- "sh": "\u079D"
- # THAANA EXTENSION FOR ARABIC LETTER SAADHU
- "S\u0323": "\u079E"
- "s\u0323": "\u079E"
- # THAANA EXTENSION FOR ARABIC LETTER TO
- "T\u0324": "\u07A0"
- "t\u0324": "\u07A0"
- # THAANA EXTENSION FOR ARABIC LETTER ZO
- "D\u0332": "\u07A1"
- "d\u0332": "\u07A1"
- # THAANA EXTENSION FOR ARABIC LETTER AINU
- "\u02BB": "\u07A2"
- # THAANA EXTENSION FOR ARABIC LETTER GHAINU
- "GH": "\u07A3"
- "Gh": "\u07A3"
- "ghgh": "\u0787\u07B0\u07A3"
- "gh": "\u07A3"
- # THAANA EXTENSION FOR ARABIC LETTER QAAFU
- "Q": "\u07A4"
- "qq": "\u0787\u07B0\u07A4"
- "q": "\u07A4"
- # THAANA EXTENSION FOR ARABIC LETTER WAAVU (NEWER LETTER)
- "W": "\u07A5"
- "ww": "\u0787\u07B0\u07A5"
- "w": "\u07A5"
- # INITIAL (AND UPPERCASE) VOWELS THAT CONVERT
- # TO ALIF FOLLOWED BY VOWEL (ALIF OMITTED IN ROMANIZATION)
- "%A\u0304": "\u0787\u07A7"
- "%A": "\u0787\u07A6"
- "\u0020a\u0304": "\u0020\u0787\u07A7"
- "\u0020a": "\u0020\u0787\u07A6"
- "%E\u0304": "\u0787\u07AD"
- "%E": "\u0787\u07AC"
- "\u0020e\u0304": "\u0020\u0787\u07AD"
- "\u0020e": "\u0020\u0787\u07AC"
- "%I\u0304": "\u0787\u07A9"
- "%I": "\u0787\u07A8"
- "\u0020i\u0304": "\u0020\u0787\u07A9"
- "\u0020i": "\u0020\u0787\u07A8"
- "%O\u0304": "\u0787\u07AF"
- "%O": "\u0787\u07AE"
- "\u0020o\u0304": "\u0020\u0787\u07AF"
- "\u0020o": "\u0020\u0787\u07AE"
- "%U\u0304": "\u0787\u07AB"
- "%U": "\u0787\u07AB"
- "\u0020u\u0304": "\u0020\u0787\u07AB"
- "\u0020u": "\u0020\u0787\u07AB"
- # THAANA MEDIAL OR FINAL VOWELS OVER ANY CONSONANT
- # (THIS ASSUMES NO UPPERCASE VOWELS REMAIN)
- "a\u0304": "\u07A7"
- "a": "\u07A6"
- "e\u0304": "\u07AD"
- "e": "\u07AC"
- "i\u0304": "\u07A9"
- "i": "\u07A8"
- "o\u0304": "\u07AF"
- "o": "\u07AE"
- "u\u0304": "\u07AB"
- "u": "\u07AB"
- # THAANA SUKUN (SILENCE) MARK; ONLY GENERATED IN OTHER COMBINATIONS
- # "": "\u07B0"
- script_to_roman:
- map:
- # THAANA LETTER NOONU WITHOUT SUKUN FOLLOWED BY A CONSONANT
- # IS ROMANIZED AS "m"+ DOT ABOVE (0307) THEN THE CONSONANT
- # OTHERWISE LETTER NOONU MAPS TO "n"
- "\u0782\u0780": "m\u0307\u0780"
- "\u0782\u0781": "m\u0307\u0781"
- "\u0782\u0783": "m\u0307\u0783"
- "\u0782\u0784": "m\u0307\u0784"
- "\u0782\u0785": "m\u0307\u0785"
- "\u0782\u0786": "m\u0307\u0786"
- "\u0782\u0788": "m\u0307\u0788"
- "\u0782\u0789": "m\u0307\u0789"
- "\u0782\u078A": "m\u0307\u078A"
- "\u0782\u0791": "m\u0307\u0791"
- "\u0782\u078B": "m\u0307\u078B"
- "\u0782\u078C": "m\u0307\u078C"
- "\u0782\u078D": "m\u0307\u078D"
- "\u0782\u078E": "m\u0307\u078E"
- "\u0782\u078F": "m\u0307\u078F"
- "\u0782\u0790": "m\u0307\u0790"
- "\u0782\u0792": "m\u0307\u0792"
- "\u0782\u0794": "m\u0307\u0794"
- "\u0782\u0795": "m\u0307\u0795"
- "\u0782\u0796": "m\u0307\u0796"
- "\u0782\u0797": "m\u0307\u0797"
- "\u0782\u0798": "m\u0307\u0798"
- "\u0782\u0799": "m\u0307\u0799"
- "\u0782\u079A": "m\u0307\u079A"
- "\u0782\u079B": "m\u0307\u079B"
- "\u0782\u079C": "m\u0307\u079C"
- "\u0782\u079D": "m\u0307\u079D"
- "\u0782\u079E": "m\u0307\u079E"
- "\u0782\u07A0": "m\u0307\u07A0"
- "\u0782\u07A1": "m\u0307\u07A1"
- "\u0782\u07A2": "m\u0307\u07A2"
- "\u0782\u07A3": "m\u0307\u07A3"
- "\u0782\u07A4": "m\u0307\u07A4"
- "\u0782\u07A5": "m\u0307\u07A5"
- # THAANA FINAL ALIFU WITH SUKUN (SILENCE) MARK
- # IS ROMANIZED WITH "h"+LOW LINE (0332)
- "\u0787\u07B0\u0020": "h\u0332\u0020"
- # THAANA SHAVIYANI WITH SUKUN (SILENCE) MARK
- # IS ROMANIZED WITH "h"+BREVE BELOW
- "\u0781\u07B0": "h\u032E"
- "\u0787\u07B0\u0780": "hh"
- "\u0780": "h"
- # THAANA ALIF WITH SUKUN AND SHAVIYANI
- "\u0787\u07B0\u0781": "s\u0301s\u0301"
- "\u0787\u07B0": "h\u0332"
- "\u0781": "s\u0301"
- "\u0787\u07B0\u0782": "nn"
- "\u0782": "n"
- "\u0787\u07B0\u0783": "rr"
- "\u0783": "r"
- "\u0787\u07B0\u0784": "bb"
- "\u0784": "b"
- "\u0787\u07B0\u0785": "l\u0323"
- "\u0785": "l\u0323"
- "\u0787\u07B0\u0786": "kk"
- "\u0786": "k"
- "\u0787\u07B0\u0788": "vv"
- "\u0788": "v"
- "\u0787\u07B0\u0789": "mm"
- "\u0789": "m"
- "\u0787\u07B0\u078A": "ff"
- "\u078A": "f"
- # THAANA LETTER "D/d" WITH DOT BELOW (0323)
- "\u0787\u07B0\u0791": "d\u0323d\u0323"
- "\u0791": "d\u0323"
- "\u0787\u07B0\u078B": "dd"
- "\u078B": "d"
- # THAANA LETTER "T/t" WITH DOT BELOW (0323)
- "\u078C\u07B0\u078C": "t\u0324t"
- "\u0787\u07B0\u078C": "tt"
- "\u0793": "t\u0323"
- "\u078C": "t"
- "\u0787\u07B0\u078D": "ll"
- "\u078D": "l"
- "\u0787\u07B0\u078E": "gg"
- "\u078E": "g"
- # THAANA LETTER "N/n' WITH TILDE (0303)
- "\u0787\u07B0\u078F": "n\u0303n\u0303"
- "\u078F": "n\u0303"
- "\u0787\u07B0\u0790": "ss"
- "\u0790": "s"
- "\u0787\u07B0\u0792": "zz"
- "\u0792": "z"
- "\u0787\u07B0\u0794": "yy"
- "\u0794": "y"
- "\u0787\u07B0\u0795": "pp"
- "\u0795": "p"
- "\u0787\u07B0\u0796": "jj"
- "\u0796": "j"
- "\u0787\u07B0\u0797": "cc"
- "\u0797": "c"
- # THAANA EXTENSION FOR ARABIC LETTER TTAA
- "\u0787\u07B0\u0798": "thth"
- "\u0798": "th"
- # THAANA EXTENSION FOR ARABIC LETTER HHAA
- "\u0787\u07B0\u0799": "h\u0323h\u0323"
- "\u0799": "h\u0323"
- # THAANA EXTENSION FOR ARABIC LETTER KHAA
- "\u0787\u07B0\u079A": "khkh"
- "\u079A": "kh"
- # THAANA EXTENSION FOR ARABIC LETTER THAALU
- "\u0787\u07B0\u079B": "dhdh"
- "\u079B": "dh"
- # THAANA EXTENSION FOR ARABIC LETTER ZAA (NEWER LETTER)
- "\u0787\u07B0\u079C": "z\u0332z\u0332"
- "\u079C": "z\u0332"
- # THAANA EXTENSION FOR ARABIC LETTER SHEENU
- "\u0787\u07B0\u079D": "shsh"
- "\u079D": "sh"
- # THAANA EXTENSION FOR ARABIC LETTER SAADHU
- "\u0787U": "07B0\u079E=s\u0323s\u0323"
- "\u079E": "s\u0323"
- # THAANA EXTENSION FOR ARABIC LETTER TO
- "\u0787U": "07B0\u07A0=t\u0324t\u0324"
- "\u07A0": "t\u0324"
- # THAANA EXTENSION FOR ARABIC LETTER ZO
- "\u0787U": "07B0\u07A1=d\u0332d\u0332"
- "\u07A1": "d\u0332"
- # THAANA EXTENSION FOR ARABIC LETTER AINU
- "\u0787U": "07B0\u07A2=\u02BB\u02BB"
- "\u07A2": "\u02BB"
- # THAANA EXTENSION FOR ARABIC LETTER GHAINU
- "\u0787\u07B0\u07A3": "ghgh"
- "\u07A3": "gh"
- # THAANA EXTENSION FOR ARABIC LETTER QAAFU
- "\u0787\u07B0\u07A4": "qq"
- "\u07A4": "q"
- # THAANA EXTENSION FOR ARABIC LETTER WAAVU (NEWER LETTER)
- "\u0787\u07B0\u07A5": "ww"
- "\u07A5": "w"
- # INITIAL VOWELS FOLLOWING ALIF (ALIF OMITTED IN ROMANIZATION)
- "\u0020\u0787\u07A7": "\u0020a\u0304"
- "\u0020\u0787\u07A6": "\u0020a"
- "\u0020\u0787\u07AD": "\u0020e\u0304"
- "\u0020\u0787\u07AC": "\u0020e"
- "\u0020\u0787\u07A9": "\u0020i\u0304"
- "\u0020\u0787\u07A8": "\u0020i"
- "\u0020\u0787\u07AF": "\u0020o\u0304"
- "\u0020\u0787\u07AE": "\u0020o"
- "\u0020\u0787\u07AB": "\u0020u\u0304"
- "\u0020\u0787\u07AB": "\u0020u"
- # THAANA ALIF APPEARING MEDIALLY WITH ANY VOWEL
- # IS ROMANIZED WITH APOSTROPHE FOLLOWED BY THE SAME VOWEL
- "\u0787\u07A7": "\u0027a\u0304"
- "\u0787\u07A6": "\u0027a"
- "\u0787\u07AD": "\u0027e\u0304"
- "\u0787\u07AC": "\u0027e"
- "\u0787\u07A9": "\u0027i\u0304"
- "\u0787\u07A8": "\u0027i"
- "\u0787\u07AF": "\u0027o\u0304"
- "\u0787\u07AE": "\u0027o"
- "\u0787\u07AB": "\u0027u\u0304"
- "\u0787\u07AB": "\u0027u"
- # THAANA MEDIAL OR FINAL VOWELS OVER CONSONANTS EXCEPT ALIF
- # THIS PRODUCES NO UPPERCASE UPPERCASE VOWELS
- "\u07A7": "a\u0304"
- "\u07A6": "a"
- "\u07AD": "e\u0304"
- "\u07AC": "e"
- "\u07A9": "i\u0304"
- "\u07A8": "i"
- "\u07AF": "o\u0304"
- "\u07AE": "o"
- "\u07AB": "u\u0304"
- "\u07AB": "u"
- # THAANA LETTER ALIF--ANY REMAINING AFTER CONVERSION MAP TO APOSTROPHE
- "\u0787": "\u0027"
|